© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128278
    Prev
    Next
    INDEX
    Explanations

    what questions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    demonstratives pointing to specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    麾
    0.40
     प्रतिरक्षा
    0.39
    ける
    0.36
    雏
    0.35
    皚
    0.34
    约
    0.34
     '+':
    0.34
     অপরি
    0.34
     उजागर
    0.33
    約
    0.33
    POSITIVE LOGITS
     dieses
    0.52
     هذه
    0.49
     diesem
    0.48
     acest
    0.46
    ttt
    0.43
     wannan
    0.42
     dieser
    0.41
     येथील
    0.41
    ববার
    0.41
    ansu
    0.40
    Activations Density 0.066%

    No Known Activations